DocumentCode
2613786
Title
Recurrent neural networks in systems identification
Author
Jubien, Chris M. ; Dimopoulos, Nikitas J.
Author_Institution
Dept. of Electr. & Comput. Eng., Victoria Univ., BC, Canada
fYear
1993
fDate
3-6 May 1993
Firstpage
2458
Abstract
A training procedure for a class of neural networks that are asymptotically stable is presented. The training procedure is a gradient method which adapts the interconnection weights as well as the relaxation constants and the slopes of the activation functions used so that the error between the expected and obtained responses is minimized. A method for assuring that stability is maintained throughout the training procedure is also given. Such a network was used to identify the dynamic behavior of a boat based on collected rudder/heading data
Keywords
asymptotic stability; identification; learning (artificial intelligence); recurrent neural nets; activation functions; asymptotically stable; boat; gradient method; interconnection weights; recurrent neural networks; relaxation constants; rudder/heading data; systems identification; training procedure; Boats; Control systems; Cost function; Gradient methods; Intelligent networks; Neural networks; Nonlinear control systems; Nonlinear systems; Recurrent neural networks; System identification;
fLanguage
English
Publisher
ieee
Conference_Titel
Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on
Conference_Location
Chicago, IL
Print_ISBN
0-7803-1281-3
Type
conf
DOI
10.1109/ISCAS.1993.394262
Filename
394262
Link To Document